INDEX

Explanations

questions related to locations, amounts, and specifics in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åªĴ

-0.16

rone

-0.15

æĹ¦

-0.15

endi

-0.14

won

-0.14

elmet

-0.14

.Designer

-0.14

ounds

-0.14

primer

-0.14

ãĤ«ãĥ«

-0.14

POSITIVE LOGITS

erture

0.18

pun

0.16

zo

0.15

 they

0.15

you

0.15

oldt

0.14

itzer

0.14

we

0.14

Activations Density 0.185%

questions related to locations, amounts, and specifics in various contexts

No Comments

No Known Activations